Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Deep neural network-based baby cry identification method and system

A deep neural network and sound recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of small scale, few successful applications, and difficulty in fully mining the law of babies' crying, so as to achieve the effect of improving the recognition rate

Active Publication Date: 2015-02-11
SHANGHAI ZHANGMEN TECH
View PDF8 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The research on baby crying recognition has appeared since the 1960s and 1970s. Limited by the previous technical level and data scale, there are not many products and technologies with application prospects, and most of the products on the market have unreliable recognition performance and technical problems. Disadvantages such as low content
On the one hand, this is due to the small scale of baby crying data collection and labeling in history, some even have only dozens of audio segments, and usually only effective identification of crying types with large differences, such as healthy babies and deaf children The recognition of crying sounds is difficult to fully explore the laws behind the crying of babies, and the reliability of distinguishing more states is not high; The modeling ability is limited, and the baby's crying sound cannot be fully modeled, so the recognition rate of the finite state is not high, and there are few successful applications.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Deep neural network-based baby cry identification method and system
  • Deep neural network-based baby cry identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Such as figure 1 As shown, the present invention provides a baby cry recognition method based on a deep neural network, including steps S1 to S8.

[0036] Step S1, collecting baby crying data for training;

[0037] Preferably, before step S3, it may also include:

[0038] Step S2, performing preprocessing for removing noise and background speech on the baby crying data for training.

[0039] Step S3, classifying and labeling the baby crying data for training;

[0040] Preferably, the classification annotations include pathological baby crying and non-pathological baby crying. Specifically, the collection, classification and labeling of baby crying data can be carried out in a professional children's hospital, and about 2 minutes of crying audio is recorded for each baby, and the parenting experts determine the reason for the baby's crying, and classify all the reasons as pathological and non-pathological categories, and mark the audio. After all the recording data ...

Embodiment 2

[0051] Such as figure 2 As shown, the present invention also provides another baby cry recognition system based on a deep neural network, including a first acquisition module 1, a labeling module 2, a first extraction module 3, an initial weight module 4, a cry model module 5, The second collection module 6 , the cry recognizer module 7 .

[0052] The first collection module 1 is used for collecting the baby's cry data for training;

[0053] Labeling module 2, for classifying and labeling the baby crying data for the training;

[0054] Preferably, the labeling module 2 is further configured to preprocess the training baby crying data by removing noise and background speech before classifying and labeling the training baby crying data.

[0055] Preferably, the classification labeling performed by the labeling module 2 includes pathological baby crying sounds and non-pathological baby crying sounds.

[0056] The first extraction module 3 is used to extract the Mel-domain cep...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a deep neural network-based baby cry identification method and a deep neural network-based baby cry identification system. The method comprises the following steps of acquiring baby cry data for training; performing classification and labeling on the baby cry data for training; extracting a Mel-domain cepstrum coefficient of each segment of audio in each piece of classified and labeled baby cry data for training to generate a data file for training; obtaining an initial weight of each layer in a deep neural network in a layer-wise pre-training way according to the data file for training; acquiring a deep neural network-based cry model according to the initial weights of all the layers in the deep neural network by virtue of a BP (back-propagation) algorithm; acquiring baby cry data to be identified, and extracting a Mel-domain cepstrum coefficient of each segment of audio in the baby cry data to be identified; performing cry identification according to the Mel-domain cepstrum coefficient of each segment of audio in the baby cry data to be identified and the cry model. According to the method and the system, the baby cry identification rate can be increased.

Description

technical field [0001] The invention relates to a method and system for recognizing baby crying sounds based on a deep neural network. Background technique [0002] The research on baby crying recognition has appeared since the 1960s and 1970s. Limited by the previous technical level and data scale, there are not many products and technologies with application prospects, and most of the products on the market have unreliable recognition performance and technical problems. Low content and other shortcomings. On the one hand, this is due to the small scale of baby crying data collection and labeling in history, some even have only dozens of audio segments, and usually only effective identification of crying types with large differences, such as healthy babies and deaf children The recognition of crying sounds is difficult to fully explore the laws behind the crying of babies, and the reliability of distinguishing more states is not high; However, the modeling ability is limi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/06G10L15/16G10L25/24
Inventor 景亚鹏张峰吴义坚
Owner SHANGHAI ZHANGMEN TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products